analiza aiqbench
This research addresses the brittleness of end-to-end learning in high-precision robotic manipulation by combining autonomous data collection for contact-rich segments with offline reinforcement learning. The proposed modular approach integrates these learned local policies with classical motion planning, achieving a 96% success rate on long-horizon assembly tasks while significantly reducing applied forces and improving generalization to out-of-distribution scenes.
Learning Where it Matters: Autonomous Data Collection and Offline Reinforcement Learning for Local Contact-Rich Manipulation
arXiv:2607.15982v2 Announce Type: replace Abstract: Learned policies trained end-to-end on large datasets often remain brittle in high-precision contact-rich tasks. Further, they typically require large amounts of manually collected data and still struggle to generalize to scenes outside of the training scenarios. Classical motion planning, in turn, generalizes well but lacks the precision and contact awareness for tight-tolerance tasks. To reliably solve challenging contact-rich tasks, we propose to leverage robot data and learning where it matters in a modular approach. First, we introduce an autonomous data collection scheme for the real world that collects dense data locally in the contact-rich segment of the task, eliminating reliance on a teleoperator's skill. Second, we show that using offline RL, the collected data can be translated into policies with high success rates. We then integrate our local policies with traditional motion planning to solve long-horizon assembly tasks. Across four real-world tasks, using only 2-2.5 h of autonomous data collection, we achieve an average success rate of 96% for long-horizon tasks, compared to 55% for a planning-only baseline and 37% for the strongest end-to-end baseline. Our local policies also reduce applied forces by 49%. Notably, performance remains at 90% for scene-level out-of-distribution scenarios, while end-to-end approaches struggle. In total, we run over 1500 real-world evaluation rollouts. Our results pave the way for targeted data collection in contact-rich tasks and for high success rates in precision applications. Videos and qualitative results are available at https://learnsyslab.github.io/data_and_learning_where_it_matters/
Abstract:Learned policies trained end-to-end on large datasets often remain brittle in high-precision contact-rich tasks. Further, they typically require large amounts of manually collected data and still struggle to generalize to scenes outside of the training scenarios. Classical motion planning, in turn, generalizes well but lacks the precision and contact awareness for tight-tolerance tasks. To reliably solve challenging contact-rich tasks, we propose to leverage robot data and learning where it matters in a modular approach. First, we introduce an autonomous data collection scheme for the real world that collects dense data locally in the contact-rich segment of the task, eliminating reliance on a teleoperator's skill. Second, we show that using offline RL, the collected data can be translated into policies with high success rates. We then integrate our local policies with traditional motion planning to solve long-horizon assembly tasks. Across four real-world tasks, using only 2-2.5 h of autonomous data collection, we achieve an average success rate of 96% for long-horizon tasks, compared to 55% for a planning-only baseline and 37% for the strongest end-to-end baseline. Our local policies also reduce applied forces by 49%. Notably, performance remains at 90% for scene-level out-of-distribution scenarios, while end-to-end approaches struggle. In total, we run over 1500 real-world evaluation rollouts. Our results pave the way for targeted data collection in contact-rich tasks and for high success rates in precision applications. Videos and qualitative results are available at this https URL
Robotics (cs.RO)
arXiv:2607.15982 [cs.RO]
(or arXiv:2607.15982v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.15982 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 327 cuvinte
Subiecte conexe
LEACL: LLM-Enhanced Automatic Curriculum Learning for Reinforcement Learning in Long-Horizon Manipulation Tasks
arXiv · 28 iul. 2026
RLMM-Flow: A Flow-based Mobile Manipulation Framework with Latent-Space Reinforcement Learning
arXiv · 30 iul. 2026
Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation
arXiv · 3 iun. 2026
When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning
arXiv · 9 oct. 2026